Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs

• URL: http://arxiv.org/abs/2106.00327v1
• Date: Tue, 1 Jun 2021 09:01:22 GMT
• Title: Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
• Authors: Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang and Xueqi Cheng
• Abstract summary: We propose CluSTeR to predict future facts in a two-stage manner, Clue Searching and Temporal Reasoning. CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts. At the temporal reasoning stage, it adopts a graph convolution network based sequence method to deduce answers from clues.
• Score: 56.33651635705633
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal Knowledge Graphs (TKGs) have been developed and used in many different areas. Reasoning on TKGs that predicts potential facts (events) in the future brings great challenges to existing models. When facing a prediction task, human beings usually search useful historical information (i.e., clues) in their memories and then reason for future meticulously. Inspired by this mechanism, we propose CluSTeR to predict future facts in a two-stage manner, Clue Searching and Temporal Reasoning, accordingly. Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts. At the temporal reasoning stage, it adopts a graph convolution network based sequence method to deduce answers from clues. Experiments on four datasets demonstrate the substantial advantages of CluSTeR compared with the state-of-the-art methods. Moreover, the clues found by CluSTeR further provide interpretability for the results.

Related papers

• HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph [14.832067253514213]
  We propose the Historical Information Passing (HIP) network to predict future events. Our method considers the updating of relation representations and adopts three scoring functions corresponding to the above dimensions. Experimental results on five benchmark datasets show the superiority of HIP network.
  arXiv  Detail & Related papers  (2024-02-19T11:50:30Z)
• Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation [59.417443739208146]
  We propose a new event forecasting model based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities. We evaluate our proposed model on five benchmark graphs.
  arXiv  Detail & Related papers  (2023-08-29T03:26:38Z)
• A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects [73.44022660932087]
  temporal characteristics are prominently evident in a substantial volume of knowledge. The continuous emergence of new knowledge, the weakness of the algorithm for extracting structured information from unstructured data, and the lack of information in the source dataset are cited. The task of Temporal Knowledge Graph Completion (TKGC) has attracted increasing attention, aiming to predict missing items based on the available information.
  arXiv  Detail & Related papers  (2023-08-04T16:49:54Z)
• DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning [46.16322824448241]
  We propose an adaptive reinforcement learning model based on attention mechanism (DREAM) to predict missing elements in the future. Experimental results demonstrate DREAM outperforms state-of-the-art models on public dataset.
  arXiv  Detail & Related papers  (2023-04-08T10:57:37Z)
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal [57.8455911689554]
  Knowledge graph reasoning (KGR) aims to deduce new facts from existing facts based on mined logic rules underlying knowledge graphs (KGs) It has been proven to significantly benefit the usage of KGs in many AI applications, such as question answering, recommendation systems, and etc.
  arXiv  Detail & Related papers  (2022-12-12T08:40:04Z)
• Temporal Knowledge Graph Completion: A Survey [24.35073672695095]
  Knowledge graph completion (KGC) can predict missing links and is crucial for real-world knowledge graphs. Recent methods have shown improved predictive results by further incorporating the timestamps of facts.
  arXiv  Detail & Related papers  (2022-01-16T05:43:49Z)
• TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting [12.963769928056253]
  We propose the first reinforcement learning method for forecasting. Specifically, the agent travels on historical knowledge graph snapshots to search for the answer. Our method defines a relative time encoding function to capture the timespan information, and we design a novel time-shaped reward based on Dirichlet distribution to guide the model learning. We evaluate our method for this link prediction task at future timestamps.
  arXiv  Detail & Related papers  (2021-09-09T08:41:01Z)
• Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks [8.317441990017924]
  We propose a new representation learning model for temporal knowledge graphs, namely CyGNet, based on a novel timeaware copy-generation mechanism. CyGNet is able to predict future facts from the whole entity vocabulary, but also capable of identifying facts with repetition and accordingly predicting such future facts with reference to the known facts in the past.
  arXiv  Detail & Related papers  (2020-12-15T18:38:03Z)
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications [89.78089494738002]
  We review research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning, are reviewed. We explore several emerging topics, including meta learning, commonsense reasoning, and temporal knowledge graphs.
  arXiv  Detail & Related papers  (2020-02-02T13:17:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.